CN109872499A - A kind of block in-situ monitor alarm system based on image recognition - Google Patents
A kind of block in-situ monitor alarm system based on image recognition Download PDFInfo
- Publication number
- CN109872499A CN109872499A CN201811586332.7A CN201811586332A CN109872499A CN 109872499 A CN109872499 A CN 109872499A CN 201811586332 A CN201811586332 A CN 201811586332A CN 109872499 A CN109872499 A CN 109872499A
- Authority
- CN
- China
- Prior art keywords
- image
- block
- floating drum
- pixel
- channel
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E30/00—Energy generation of nuclear origin
Abstract
The block in-situ monitor alarm system based on image recognition that the present invention provides a kind of, belongs to image recognition monitoring technical field, the monitoring, alarming work for blocking in place for nuclear plant water intaking mouth.The present invention includes that outdoor images monitoring system and off-the-air picture identify alarm system two parts.Outdoor images monitoring system is responsible for the state in place of monitoring block.The video image that off-the-air picture identification alarm system monitors, image recognition algorithm has simultaneously formulated block failure discrimination standard algorithm, it can identify position and the quantity of the upper crocus floating drum of image judgement block, and then determine the working condition of block, and alarm signal can be issued by alarm in the case where determining dangerous situation.The present invention establishes a kind of alarm system in place of the block based on image monitoring and image recognition, can differentiate the working condition of block by the position and number of identification floating drum, and can in case of emergency issue alarm signal, staff is made to make emergency processing in time.
Description
Technical field
The invention belongs to image recognition monitoring technical fields, are related specifically to monitoring in place of blocking at nuclear plant water intaking mouth
Alert operation.
Background technique
Most of nuclear power plant reactor uses presurized water reactor, stand interior reactor recirculating cooling water system and important equipment it is cold
But use water using intake as water source.But in summer, ocean temperature is higher, marine growth mass propagation.Extracting cooling water mistake
Cheng Zhong, a large amount of marine growths can enter water plant by channel of fetching water, and blocking drum type filter screen causes pressure difference to be alarmed, then causes to stop
Machine, shutdown cause huge economic loss.For this purpose, nuclear power station arranges garbage barrier net in intake irrigation channel front end, to intercept
Irrigation channel rubbish, sundries and aquatic organism etc. ensure nuclear power station unit station safe operation.Block by online attachment, stormy waves and
Under the joint effect of tide etc., easily there is situations such as pulling force overload causes main fracture of rope, major network cracking, to make a large amount of aquatic
The sundries such as object and sea grass enter intake, and the safe operation for influencing nuclear power causes huge economic losses.It, can be right for this situation
Block carries out realtime graphic monitoring, and warning note is made in the case where crack conditions occurs in block, and staff can make emergency processing,
The emergencies such as shutdown are avoided to occur.
Summary of the invention
The block in-situ monitor alarm system based on image recognition that the present invention provides a kind of, being capable of real-time monitoring block work
Make state, ensures that nuclear power plant reactor cold source work safety carries out.This monitor and alarm system mainly has outdoor image monitoring system
With off-the-air picture identification alarm system two parts composition.Outdoor images monitor system and use video camera real-time monitoring block work feelings
Condition constructs local area network using Homeplug, block monitoring image is transferred to off-the-air picture identification alarm system, by system computerized
End image recognition software carries out the assessment of block working condition.This image recognition software optimizes image recognition algorithm and formulates
Block failure discrimination standard, such as determines emergency, then starts warning device immediately, staff is reminded to make at emergency
Reason.
Technical solution of the present invention:
A kind of block in-situ monitor alarm system based on image recognition, including outdoor images monitoring system and off-the-air picture
Identify alarm system two parts；
Acquisition of the outdoor images monitoring system for video image of blocking, and block video image information is transferred to room
Interior image identification alarm system carries out discriminance analysis；System is blocked work real time status using camera record, and by picture number
According to being saved in the hard disk drive in waterproof distribution box；Since seashore humidity is larger, so to use waterproof distribution box storage system
Equipment；
Small-scale LAN is established using Homeplug and router, the image information of outdoor images monitoring system passes through power line
It is transferred to off-the-air picture identification alarm system；Using power line transmission, steady signal transmission, can overcome wireless transmission signal compared with
The shortcomings that difference, image is easy frame losing.
Alarm in the case of identification and block operation irregularity of the off-the-air picture identification alarm system for monitoring image of blocking；
Outdoor block working condition image is transferred to indoor computer end image recognition software, carries out identifying processing to image.Outdoor block
It is mainly made of main rope, dictyosome and block floating drum, dictyosome and floating drum are all tied on main rope.If main rope is broken, net
Body and floating drum can at sea be floated with main rope.The outdoor main rope of block and dictyosome are white, and floating drum is Chinese red, and software can pass through knowledge
The position of the more apparent Chinese red floating drum of color and number differentiate whether block is broken in other image.Such as pontoon position
It is different from software built-in buoy number beyond regulation boundary or floating drum number, then alarm signal is issued by alarm immediately.
It elaborates below to image recognition section in off-the-air picture identification alarm system:
In the daytime block image recognition scheme:
The identification of block floating drum is mainly based upon HSV space color model principle and is identified that HSV space color model is straight
The tone (H) for reflecting image, saturation degree (S) and the lightness (V) seen；Tone (H) is expressed as the color of image, saturation degree
(S) it is expressed as the bright-coloured degree of color, lightness (V) is expressed as the bright-dark degree of image；
Amount again is carried out primarily directed to three tone (H), saturation degree (S) and lightness (V) channels in identification process
Change, and the actual condition at nuclear power station scene is combined to formulate different recognizers, is required with meeting identification, specific as follows:
P (x, y)=(P (x-1, y-1)+P (x, y-1)+P (x+1, y-1)+P (x+1, y)+P (x+1, y+1)+P (x, y+1)+
P (x-1, y+1)+P (x-1, y))/8 (1)
Above-mentioned formula is the fuzzy algorithmic approach of image, that is, passes through 8 neighborhoods (8 pixels adjacent with the pixel) of some pixel
Average value determine the color value of the pixel；In formula: x is the x-axis coordinate of each pixel in the picture, and y is each
The y-axis coordinate of pixel in the picture, P (x, y) are the color value of each pixel in image, and the expression formula of right side of the equal sign is should
The average value of 8 neighborhood of pixel；
V (x, y)=(V (x, y)-Vmin(x, y))/(Vmax(x, y)-Vmin(x, y)) (2)
Above-mentioned formula is that the channel HSV image brightness (V) re-quantization algorithm obtains that is, by the channel V of whole image of statistics
The maximum value and minimum value in the channel V out, is normalized operation to the channel V again；In formula: x is that each pixel is being schemed
X-axis coordinate as in, y are the y-axis coordinate of each pixel in the picture, and V (x, y) is the value in the channel V of each pixel,
Vmin(x, y) is the minimum value in the channel V on whole image, Vmax(x, y) is the maximum value in the channel V on whole image；
S (x, y)=(S (x, y)-Smin(x, y))/(Smax(x, y)-Smin(x, y)) (3)
Above-mentioned formula is the channel HSV image saturation (S) re-quantization algorithm, i.e., by counting the channel S of whole image,
The maximum value and minimum value for obtaining channel S, are normalized operation to channel S again；In formula: x is that each pixel exists
X-axis coordinate in image, y are the y-axis coordinate of each pixel in the picture, and S (x, y) is the channel V of each pixel
Value, Smin(x, y) is the minimum value of channel S on whole image, Smax(x, y) is the maximum value of channel S on whole image.
Above-mentioned formula is the channel HSV picture tone H re-quantization algorithm, i.e., is recalculated by the range of red tone
The value in the channel H, if the value in the channel H of some pixel in red minimum value and red average value ranges, by the pixel
The value in the channel H be revised as red average value；If do not changed in red average value and red maximum range
The value in the channel H of the pixel, to improve the purity of red color tone；In formula: x is the x-axis coordinate of each pixel in the picture, y
For the y-axis coordinate of each pixel in the picture, H (x, y) is the value in the channel H of each pixel, Hred(min)For red color tone
The minimum value of range, Hred(max)For the maximum value of red color tone range, Hred(avg)For the average value of red color tone range；
Above-mentioned formula is Image binarizing algorithm, i.e., by the threshold value in each channel of HSV image by the prospect and background of image
Separation；In formula: x is the x-axis coordinate of each pixel in the picture, and y is the y-axis coordinate of each pixel in the picture, P
(x, y) is the pixel value of image, HT(min)、HT(max)For the minimum threshold and max-thresholds in the channel H, ST(min)、ST(max)It is logical for S
The minimum threshold and max-thresholds in road, VT(min)、VT(max)For the minimum threshold and max-thresholds in the channel V；
The original image that system provides is monitored according to outdoor images, block image is analyzed and processed, identifies block
The position and number of floating drum provides foundation for the assessment and early warning of subsequent block state.Specific identifying schemes are as follows:
Due to field working conditions complexity, disturbed condition is more, so needing to carry out image before recognition at fuzzy noise reduction
Reason.Image acquired in video capture device is obscured, by above-mentioned formula (1), traverses all pictures of entire image
Element recalculates each pixel value, can be by water surface foreign matter in image, water surface ripple and the reflective unusual face for waiting parts of the water surface
Color value filters away, reduces interference of the noise to identification.
HSV space color model image will be mapped to by the filtered RGB color model image of fuzzy algorithmic approach.Root
According to the fixation location information at block nettle both ends, block image is split, and extracts key area, which is comprising whole
All floating drums of item block.The extraction of key area is convenient for so that the image of processing becomes a small image from big image into one
Step processing, it is possible to reduce the interference of the garbages such as dykes and dams, and can sufficiently reduce the processing time.
According to block floating drum color and HSV space color model feature, corresponding pixel quantization algorithm is formulated, to make
Floating drum of blocking is more prominent, is conducive to subsequent identification and positioning.
By above-mentioned formula (2), re-quantization, Ke Yiti are carried out to the lightness channel (V) of the key area image of extraction
The brightness level of high entire image.
By above-mentioned formula (3), re-quantization is carried out to the saturation degree channel (S) of the key area image of extraction, it can be with
Improve the bright-coloured degree of entire image.
Image can become more clearly to become clear after above-mentioned two-step pretreatment, and image is not in undistorted existing
As the form and aspect tune of i.e. image is consistent with source graph coloring tune.Next the tone of image is handled, it is therefore intended that improve certain face
Excitation purity facilitates the subsequent identification to certain color.
By above-mentioned formula (4), re-quantization is carried out to the tone channel (H) of the key area image of extraction, i.e., to figure
The color of block floating drum is modified as in, improves Exocarpium Citri Rubrum excitation purity, keeps floating drum color more prominent.
After the re-quantization of above-mentioned pixel, available one bright-coloured bright and floating drum colour purity is higher, face
The lesser block image of color range.Next binarization operation, the specified threshold to match with floating drum color are carried out to conventional images
Value range is separated the floating drum in image with other objects by above-mentioned formula (5), i.e., is set to the pixel in floating drum region black
Color, other regions are set to white, obtain a width binary image.
Profile finally is searched to the image after binaryzation, determines the number of profile and the center position of profile, profile
Number be block floating drum number, profile center position is the position of floating drum.
Night block image recognition scheme:
Since night cannot collect colored block image, so cannot use and identical identifying schemes in the daytime.Needle
Scheme to the block status monitoring at night is: setting up infrared light supply on block floating drum, acquires equipment by infrared light supply and catch
Infrared light supply is caught, by the binarization operation to image, infrared light supply is separated with other interference informations, then to binaryzation
Image searches profile, determines that the number of profile and the center position of profile, the number of profile are floating drum number of blocking, wheel
Wide center position is the position of floating drum.
Under normal primary condition, position and quantity by image recognition floating drum record pontoon position quantity information.?
In image recognition processes later, by obtained pontoon position information with it is initial when location information compare, calculate it is same
The distance between floating drum different moments can reflect block operation irregularity, triggering report when obtained distance reaches warning value
It is alert.It simultaneously in subsequent identification, such as identifies that floating drum quantity and initial frame floating drum quantity mismatch, can also indicate that block work is different
Often, triggering alarm immediately.
Technical characterstic of the invention has:
(1) present invention establishes a kind of alarm system in place of the block based on image monitoring and image recognition, can pass through knowledge
The position of other floating drum and number differentiate the working condition of block, and can in case of emergency issue alarm signal, make work people
Member makes emergency processing in time.
(2) present invention 24 hours round-the-clock monitoring block working conditions.Since night is darker, cannot clearly shoot
The position of floating drum and number information, spy are irradiated using high-power search light, and the position of floating drum can be clearly identified in evening images
It sets and number information.
(3) monitoring place of the invention by the sea, will consider the influence of wave and humidity to outdoor images monitoring system, be
This needs special waterproof distribution box, prevents short-circuit conditions.
(4) outdoor images monitoring system of the present invention uses 220v power supply power supply, and flow of personnel is larger at monitoring, staff
Inevitable touch apparatus.For safeguard work personnel safety, earth leakage protective device is installed in internal system, prevents Danger Electric shock risk.
(5) present invention establishes local area network using Homeplug and router, by power line transmission signals, so that wireless transmission
Become wire transmission, reception signal is more preferable, and image will not frame losing.
(6) present invention has write image recognition software, can identify Chinese red by each frame video image of monitoring
The position of floating drum and quantity, and with the pontoon position of software initial identification and floating drum quantitative comparison, judge block it is whether in place.
If judging that crack conditions occur for block, then alarm signal is issued by alarm, make that staff at emergency in time
Reason.
(7) optimization of related algorithm has been carried out when image recognition of the present invention, has carried out the extraction of key area, which is packet
The minimum parallel quadrangle of the floating drum containing block, it is possible to reduce the interference of the garbages such as dykes and dams in image, and can sufficiently reduce
Handle the time.
(8) present invention has formulated block failure discrimination standard algorithm, by pontoon position in each frame image of calculating and just
Whether the distance between beginning frame pontoon position reaches warning value, while identifying whether floating drum quantity matches with initial frame quantity.Two
Person has one to be unsatisfactory for condition, that is, can determine that block operation irregularity, that is, can trigger alarm.
Detailed description of the invention
Fig. 1 is that the present invention is based on the block in-situ monitor alarm system structural schematic diagrams of image recognition.
Fig. 2 is block image monitoring schematic diagram.
Fig. 3 is block image binaryzation processing figure.
Specific embodiment
The structure, manufacturing process of 1,2 pair of invention, operation implementation process are described further with reference to the accompanying drawing.
Based on the block in-situ monitor alarm system of image recognition, as shown in Figure 1, include outdoor images monitoring system and
Off-the-air picture identifies alarm system two parts.
It mainly includes waterproof distribution box, insert row, adapter, video camera, hard disk drive, earth leakage protective that outdoor images, which monitor system,
Device, Homeplug and cable.The external electrical line of force is connected to insert row through earth leakage protective device, from insert row respectively to Homeplug, hard disk drive and
Video camera power supply.Hard disk drive connects 48v adapter, and video camera connects 12v adapter.Connected between video camera and hard disk drive with cable
It connects, the realtime graphic of camera record is stored in hard disk drive.It is connected between Homeplug and hard disk drive with cable, to transmit view
Frequency image.Earth leakage protective device, adapter, insert row, hard disk drive and Homeplug are all placed in waterproof distribution box, and items connection finishes
Afterwards, waterproof distribution box is sealed, prevents from causing short circuit into water.Video camera is mounted on the designated position outside waterproof distribution box, adjusts
Whole good angle allows video camera that can take entire block region, is fixed.
Off-the-air picture identification alarm system is mainly made of power supply, alarm, computer, router and Homeplug.Power supply point
It does not power to alarm, computer, router and Homeplug, respectively with cable between computer and router, router and Homeplug
Connection.Local area network is constituted between router, indoor power cat and outdoor power cat, the block realtime graphic of outdoor-monitoring can pass through
Power line transmission carries out image recognition processing analysis to indoor computer end image recognition software.The image sketch of software processing is such as
Shown in Fig. 2, image is subjected to key area extraction and Fuzzy Processing, detects Chinese red floating drum position based on hsv color Space Principles
It sets, and image is subjected to binary conversion treatment as shown in Figure 3, then function is searched by profile and finds floating drum profile in image.It is logical
It crosses to the position of Chinese red floating drum in image and quantity identification and differentiates whether block is broken, if it is judged that block is different
Often, then alarm signal is triggered immediately.
Claims (1)
1. a kind of block in-situ monitor alarm system based on image recognition, which is characterized in that described based on image recognition
Block in-situ monitor alarm system includes outdoor images monitoring system and off-the-air picture identification alarm system two parts；
Establish Small-scale LAN, acquisition of the outdoor images monitoring system for video image of blocking, and the video image that will block
Information identifies that alarm system carries out discriminance analysis by power line transmission to off-the-air picture；Outdoor images monitor system using camera shooting
Machine record block work real time status, and image information is saved in the hard disk drive in waterproof distribution box；
Alarm in the case of identification and block operation irregularity of the off-the-air picture identification alarm system for monitoring image of blocking；It is outdoor
Block working condition image is transferred to indoor computer end, carries out identifying processing to image；Outdoor block mainly by it is main rope, dictyosome and
Floating drum of blocking forms, and dictyosome and block floating drum are all tied on main rope；If main rope is broken, dictyosome and block floating drum with
Main rope at sea floats；The main rope of outdoor block and dictyosome are white, and block floating drum is Chinese red, by identify in image color compared with
For apparent Chinese red floating drum position and number come differentiate block whether be broken；If pontoon position of blocking is beyond regulation circle
Limit or block floating drum number are different from the built-in block floating drum number of original start, then issue alarm signal by alarm immediately
Number；
It is as follows to image recognition in off-the-air picture identification alarm system:
(1) it blocks in the daytime image recognition
The identification of block floating drum is mainly based upon HSV space color model principle and is identified that HSV space color model is intuitive
Reflect the tone H, saturation degree S and lightness V of image；Tone H is expressed as the color of image, and saturation degree S is expressed as color
Bright-coloured degree, lightness V are expressed as the bright-dark degree of image；
Quantization again, and syncaryon are carried out primarily directed to tone H, saturation degree S and tri- channels lightness V in identification process
The actual condition at power station scene formulates different recognizers, is required with meeting identification, specific as follows:
P (x, y)=(P (x-1, y-1)+P (x, y-1)+P (x+1, y-1)+P (x+1, y)+P (x+1, y+1)+P (x, y+1)+P (x-
1, y+1)+P (x-1, y))/8 (1)
Above-mentioned formula is the fuzzy algorithmic approach of image, i.e., the color of the pixel is determined by the average value of 8 neighborhoods of some pixel
Value；In formula: x is the x-axis coordinate of each pixel in the picture, and y is the y-axis coordinate of each pixel in the picture, P
(x, y) is the color value of each pixel in image, and the expression formula of right side of the equal sign is the average value of 8 neighborhood of pixel；
V (x, y)=(V (x, y)-Vmin(x, y))/(Vmax(x, y)-Vmin(x, y)) (2)
Above-mentioned formula is the channel HSV image brightness V re-quantization algorithm, i.e., by the channel V of whole image of statistics, show that V is logical
The maximum value and minimum value in road, are normalized operation to the channel V again；In formula: x be each pixel in the picture
X-axis coordinate, y are the y-axis coordinate of each pixel in the picture, and V (x, y) is the value in the channel V of each pixel, Vmin(x,
It y) is the minimum value in the channel V on whole image, Vmax(x, y) is the maximum value in the channel V on whole image；
S (x, y)=(S (x, y)-Smin(x, y))/(Smax(x, y)-Smin(x, y)) (3)
Above-mentioned formula is HSV image saturation channel S re-quantization algorithm, that is, passes through the channel S of whole image of statistics, obtain S
The maximum value and minimum value in channel, are normalized operation to channel S again；In formula: x be each pixel in the picture
X-axis coordinate, y be the y-axis coordinate of each pixel in the picture, S (x, y) be each pixel the channel V value, Smin
(x, y) is the minimum value of channel S on whole image, Smax(x, y) is the maximum value of channel S on whole image；
Above-mentioned formula is the channel HSV picture tone H re-quantization algorithm, i.e., it is logical that H is recalculated by the range of red tone
The value in road, if the value in the channel H of some pixel in red minimum value and red average value ranges, by the H of the pixel
The value in channel is revised as red average value；If not changing this in red average value and red maximum range
The value in the channel H of pixel, to improve the purity of red color tone；In formula: x is the x-axis coordinate of each pixel in the picture, and y is
The y-axis coordinate of each pixel in the picture, H (x, y) are the value in the channel H of each pixel, Hred(min)For red color tone model
The minimum value enclosed, Hred(max)For the maximum value of red color tone range, Hred(avg)For the average value of red color tone range；
Above-mentioned formula is Image binarizing algorithm, i.e., by the threshold value in each channel of HSV image by the prospect and background separation of image；
In formula: x is the x-axis coordinate of each pixel in the picture, and y is the y-axis coordinate of each pixel in the picture, P (x, y)
For the pixel value of image, HT(min)、HT(max)For the minimum threshold and max-thresholds in the channel H, ST(min)、ST(max)For channel S
Minimum threshold and max-thresholds, VT(min)、VT(max)For the minimum threshold and max-thresholds in the channel V；
The original image that system provides is monitored according to outdoor images, block image is analyzed and processed, identifies block floating drum
Position and number, provide foundation for the assessment and early warning of subsequent block state；Specific identifying schemes are as follows:
(1.1) fuzzy noise reduction process is carried out to image before identification, i.e., image acquired in video capture device is obscured,
By above-mentioned formula (1), all pixels of entire image are traversed, recalculate each pixel value, by water surface foreign matter, water in image
Surface wave line and the reflective unusual color value of the water surface filter away, reduce interference of the noise to identification；
(1.2) HSV space color model image will be mapped to by the filtered RGB color model image of fuzzy algorithmic approach；
According to the fixation location information at main rope both ends of blocking, block image is split, and extract key area, which is
All block floating drums comprising whole block；The extraction of key area, so that the image of processing becomes a small figure from big image
Picture；
According to block floating drum color and HSV space color model feature, corresponding pixel quantization algorithm is formulated, to make to block
Floating drum is more prominent, is conducive to subsequent identification and positioning；
By above-mentioned formula (2), re-quantization is carried out to the channel lightness V of the key area image of extraction, for improving whole picture
The brightness level of image；
By above-mentioned formula (3), re-quantization is carried out to the saturation degree channel S of the key area image of extraction, it is whole for improving
The bright-coloured degree of width image；
Image becomes more clearly to become clear after above-mentioned two-step pretreatment, and image is not in undistorted phenomenon, that is, is schemed
The form and aspect tune of picture is consistent with source graph coloring tune；
Next the tone of image is handled, it is logical to the tone H of the key area image of extraction by above-mentioned formula (4)
Road carries out re-quantization, i.e., modifies to the color for floating drum of blocking in image, improve Exocarpium Citri Rubrum excitation purity, make floating drum color of blocking
It is more prominent；
After the re-quantization of above-mentioned pixel, obtain that one bright-coloured bright and floating drum colour purity of blocking is higher, color model
Enclose lesser block image；
(1.3) binarization operation, the specified threshold range to match with block floating drum color, by above-mentioned are carried out to conventional images
Formula (5) separates the block floating drum in image with other objects, i.e., the pixel in floating drum region of blocking is set to black, other
Region is set to white, obtains a width binary image；
(1.4) profile finally is searched to the image after binaryzation, determines the number of profile and the center position of profile, profile
Number be block floating drum number, profile center position is the position of floating drum；
(2) night block image recognition
For the block status monitoring at night: setting up infrared light supply on block floating drum, acquire equipment by infrared light supply and capture
Infrared light supply is separated infrared light supply with other interference informations, then by the binarization operation to image to binary picture
As searching profile, determine that the number of profile and the center position of profile, the number of profile are floating drum number of blocking, profile
Center position is the position of block floating drum；
Under normal primary condition, position and quantity by image recognition block floating drum, record block pontoon position quantity letter
Breath；In image recognition processes later, by obtained block pontoon position information with it is initial when location information compare,
The distance between same block floating drum different moments are calculated, reflect that block work is different when obtained distance reaches warning value
Often, triggering alarm；Simultaneously in subsequent identification, such as identify that block floating drum quantity and initial frame block floating drum quantity mismatch,
Also block operation irregularity is indicated, immediately triggering alarm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811586332.7A CN109872499B (en) | 2018-12-25 | 2018-12-25 | Block on-spot monitoring alarm system based on image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811586332.7A CN109872499B (en) | 2018-12-25 | 2018-12-25 | Block on-spot monitoring alarm system based on image recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109872499A true CN109872499A (en) | 2019-06-11 |
| CN109872499B CN109872499B (en) | 2020-09-29 |
Family
ID=66917300
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811586332.7A Expired - Fee Related CN109872499B (en) | 2018-12-25 | 2018-12-25 | Block on-spot monitoring alarm system based on image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109872499B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111931760A (en) * | 2020-07-30 | 2020-11-13 | 国网江苏省电力有限公司南通供电分公司 | Method for identifying use of safety belt on electric power operation site with special mark for backup safety rope |
| CN117409341A (en) * | 2023-12-15 | 2024-01-16 | 深圳市光明顶技术有限公司 | Unmanned aerial vehicle illumination-based image analysis method and system |
Citations (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS5932583A (en) * | 1982-08-17 | 1984-02-22 | Hitachi Zosen Corp | Mooring apparatus for buoyant body |
| CN87201346U (en) * | 1987-02-10 | 1988-05-25 | 乔新明 | Fishnet with automatic monitor |
| US5913670A (en) * | 1996-12-19 | 1999-06-22 | Anderson; Erik S. | Breakaway links for underwater gear |
| WO2006117249A2 (en) * | 2005-05-05 | 2006-11-09 | Acergy France Sa | Towing and subsea installation of long articles |
| CN101980311A (en) * | 2010-08-27 | 2011-02-23 | 国家海洋局第二海洋研究所 | Method for giving alarm to low oxygen phenomenon of inshore ocean by monitoring buoys |
| CN201800877U (en) * | 2010-02-24 | 2011-04-20 | 中华人民共和国广东海事局北海航标处 | Floating drum for buoys |
| JP4709703B2 (en) * | 2006-07-12 | 2011-06-22 | 誠一 中野 | Submersible float |
| US8177596B2 (en) * | 2010-01-22 | 2012-05-15 | Skysight Technologies Llc | Fishing trawler net resistant subsurface buoy tether system |
| CN102935883A (en) * | 2011-08-15 | 2013-02-20 | 江苏华阳重工股份有限公司 | Lever type anti-net warning device for ship |
| CN103352419A (en) * | 2013-07-03 | 2013-10-16 | 宁波大学 | Bridge pier fence netting of cross-sea bridge |
| RU144771U1 (en) * | 2013-12-09 | 2014-08-27 | Федеральное государственное бюджетное учреждение науки институт океанологии им. П.П. Ширшова Российской академии наук | DEVICE FOR MARINE SEISMO-ACOUSTIC EXPLORATION |
| CN204199244U (en) * | 2014-10-10 | 2015-03-11 | 胡健 | A kind of alarm-type trashrack on power station |
| CN205604201U (en) * | 2016-01-26 | 2016-09-28 | 云南大唐国际李仙江流域水电开发有限公司 | New parallel twin float trash rack device |
| CN205653764U (en) * | 2016-04-14 | 2016-10-19 | 大唐岩滩水力发电有限责任公司 | Movable trash device of power station water inlet |
| CN205682179U (en) * | 2016-06-23 | 2016-11-16 | 广西钦州保税港区欧博科技开发有限公司 | A kind of etting breakage-proof alarm device for marine mesh cage |
| CN205711958U (en) * | 2016-03-30 | 2016-11-23 | 中国电建集团贵阳勘测设计研究院有限公司 | Device for blocking fish before a kind of reservoir dam |
| US20170042132A1 (en) * | 2015-08-14 | 2017-02-16 | George Hallner | Trawling skimmer |
| KR101725071B1 (en) * | 2016-01-12 | 2017-04-10 | 이정구 | Float for farming |
| CN106614205A (en) * | 2016-12-15 | 2017-05-10 | 浙江海洋大学 | Flexible suspended cable type large-scale shallow-sea purse seine |
| CN107273809A (en) * | 2017-05-22 | 2017-10-20 | 哈尔滨工程大学 | A kind of method of the real-time autonomous classification of fishing net under water for power buoy |
| CN207252573U (en) * | 2017-09-02 | 2018-04-20 | 河北鑫海水产生物技术有限公司 | Coastal waters aquaculture net |
| CN207317619U (en) * | 2017-05-10 | 2018-05-04 | 耿文峰 | Block dirty strainer in a kind of fired power generating unit cooling tower basin outlet |
| CN108007499A (en) * | 2017-11-15 | 2018-05-08 | 大连理工大学 | A kind of block working state monitoring method for early warning of combination Computational Mechanics and field monitoring |
| CN207379640U (en) * | 2017-11-03 | 2018-05-18 | 辽宁红沿河核电有限公司 | The underwater garbage barrier net early warning and alarming monitoring system of nuclear power station |
| WO2018142073A1 (en) * | 2017-02-01 | 2018-08-09 | Peinture Industrielle Email Au Four Ets Biousse | System for securing a submerged beacon |
| CN108407978A (en) * | 2018-05-05 | 2018-08-17 | 青岛森科特智能仪器有限公司 | A kind of beacon system and its application method for pulling big sea buoy |
| CN207919515U (en) * | 2018-03-01 | 2018-09-28 | 三峡大学 | A kind of drainage ditch rubbish filters out autoalarm |
-
2018
- 2018-12-25 CN CN201811586332.7A patent/CN109872499B/en not_active Expired - Fee Related
Patent Citations (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS5932583A (en) * | 1982-08-17 | 1984-02-22 | Hitachi Zosen Corp | Mooring apparatus for buoyant body |
| CN87201346U (en) * | 1987-02-10 | 1988-05-25 | 乔新明 | Fishnet with automatic monitor |
| US5913670A (en) * | 1996-12-19 | 1999-06-22 | Anderson; Erik S. | Breakaway links for underwater gear |
| WO2006117249A2 (en) * | 2005-05-05 | 2006-11-09 | Acergy France Sa | Towing and subsea installation of long articles |
| JP4709703B2 (en) * | 2006-07-12 | 2011-06-22 | 誠一 中野 | Submersible float |
| US8177596B2 (en) * | 2010-01-22 | 2012-05-15 | Skysight Technologies Llc | Fishing trawler net resistant subsurface buoy tether system |
| CN201800877U (en) * | 2010-02-24 | 2011-04-20 | 中华人民共和国广东海事局北海航标处 | Floating drum for buoys |
| CN101980311A (en) * | 2010-08-27 | 2011-02-23 | 国家海洋局第二海洋研究所 | Method for giving alarm to low oxygen phenomenon of inshore ocean by monitoring buoys |
| CN102935883A (en) * | 2011-08-15 | 2013-02-20 | 江苏华阳重工股份有限公司 | Lever type anti-net warning device for ship |
| CN103352419A (en) * | 2013-07-03 | 2013-10-16 | 宁波大学 | Bridge pier fence netting of cross-sea bridge |
| RU144771U1 (en) * | 2013-12-09 | 2014-08-27 | Федеральное государственное бюджетное учреждение науки институт океанологии им. П.П. Ширшова Российской академии наук | DEVICE FOR MARINE SEISMO-ACOUSTIC EXPLORATION |
| CN204199244U (en) * | 2014-10-10 | 2015-03-11 | 胡健 | A kind of alarm-type trashrack on power station |
| US20170042132A1 (en) * | 2015-08-14 | 2017-02-16 | George Hallner | Trawling skimmer |
| KR101725071B1 (en) * | 2016-01-12 | 2017-04-10 | 이정구 | Float for farming |
| CN205604201U (en) * | 2016-01-26 | 2016-09-28 | 云南大唐国际李仙江流域水电开发有限公司 | New parallel twin float trash rack device |
| CN205711958U (en) * | 2016-03-30 | 2016-11-23 | 中国电建集团贵阳勘测设计研究院有限公司 | Device for blocking fish before a kind of reservoir dam |
| CN205653764U (en) * | 2016-04-14 | 2016-10-19 | 大唐岩滩水力发电有限责任公司 | Movable trash device of power station water inlet |
| CN205682179U (en) * | 2016-06-23 | 2016-11-16 | 广西钦州保税港区欧博科技开发有限公司 | A kind of etting breakage-proof alarm device for marine mesh cage |
| CN106614205A (en) * | 2016-12-15 | 2017-05-10 | 浙江海洋大学 | Flexible suspended cable type large-scale shallow-sea purse seine |
| WO2018142073A1 (en) * | 2017-02-01 | 2018-08-09 | Peinture Industrielle Email Au Four Ets Biousse | System for securing a submerged beacon |
| CN207317619U (en) * | 2017-05-10 | 2018-05-04 | 耿文峰 | Block dirty strainer in a kind of fired power generating unit cooling tower basin outlet |
| CN107273809A (en) * | 2017-05-22 | 2017-10-20 | 哈尔滨工程大学 | A kind of method of the real-time autonomous classification of fishing net under water for power buoy |
| CN207252573U (en) * | 2017-09-02 | 2018-04-20 | 河北鑫海水产生物技术有限公司 | Coastal waters aquaculture net |
| CN207379640U (en) * | 2017-11-03 | 2018-05-18 | 辽宁红沿河核电有限公司 | The underwater garbage barrier net early warning and alarming monitoring system of nuclear power station |
| CN108007499A (en) * | 2017-11-15 | 2018-05-08 | 大连理工大学 | A kind of block working state monitoring method for early warning of combination Computational Mechanics and field monitoring |
| CN207919515U (en) * | 2018-03-01 | 2018-09-28 | 三峡大学 | A kind of drainage ditch rubbish filters out autoalarm |
| CN108407978A (en) * | 2018-05-05 | 2018-08-17 | 青岛森科特智能仪器有限公司 | A kind of beacon system and its application method for pulling big sea buoy |
Non-Patent Citations (3)
| Title |
|---|
| CHUNHU LIU等: "Development of a Compact Marine Environmental Monitoring Module Based on SMT32", 《2012 SPRING CONGRESS ON ENGINEERING AND TECHNOLOGY》 * |
| DONG-JIING DOONG等: "Searching for freak waves from in-situ buoy measurements", 《OCENAS" 10 IEEE SYDNEY》 * |
| 李凌: "水电厂进水口浮式拦污排主绳断丝超标处理", 《红水河》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111931760A (en) * | 2020-07-30 | 2020-11-13 | 国网江苏省电力有限公司南通供电分公司 | Method for identifying use of safety belt on electric power operation site with special mark for backup safety rope |
| CN117409341A (en) * | 2023-12-15 | 2024-01-16 | 深圳市光明顶技术有限公司 | Unmanned aerial vehicle illumination-based image analysis method and system |
| CN117409341B (en) * | 2023-12-15 | 2024-02-13 | 深圳市光明顶技术有限公司 | Unmanned aerial vehicle illumination-based image analysis method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109872499B (en) | 2020-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN207820108U (en) | A kind of transmission line long-distance video monitoring system | |
| CN106407927B (en) | The significance visual method suitable for underwater target detection based on polarization imaging | |
| CN108307146A (en) | A kind of ultra-high-tension power transmission line Security Vulnerability Detecting System and method | |
| WO2022116763A1 (en) | Device and method for underwater intelligent monitoring of sand dredger | |
| CN109872499A (en) | A kind of block in-situ monitor alarm system based on image recognition | |
| Lai et al. | A real time video processing based surveillance system for early fire and flood detection | |
| CN111540173B (en) | Drowning alarm system and method based on intelligent picture recognition | |
| CN102254395A (en) | Article theft detecting and alarming device and method based on intelligent video analysis | |
| CN113887412B (en) | Detection method, detection terminal, monitoring system and storage medium for pollution emission | |
| CN101378501A (en) | Ganged monitoring apparatus for infrared panorama and control method thereof | |
| CN201467360U (en) | Detection system for exhibitting field personnel flow rate | |
| CN109660761A (en) | The personal identification of band conveyer corridor complex environment and alarm system and method based on SSD | |
| CN201237824Y (en) | Intelligent monitoring alarm system for oil well | |
| CN108492517A (en) | A kind of fire monitoring system for building | |
| CN104333745B (en) | Seashore outdoor bathing place underwater picture monitoring system waterborne | |
| CN110942577A (en) | Machine vision-based river sand stealing monitoring system and method | |
| Wang et al. | Research and application of artificial technology for substation environment surveillance system | |
| CN111416964B (en) | Remote image intelligent identification method for hydraulic engineering deformation | |
| CN204217067U (en) | Outdoor bathing place, seashore underwater picture supervisory control system waterborne | |
| CN110414342A (en) | A kind of movement human detection recognition method based on video image processing technology | |
| CN107729874B (en) | Swimming pool drowning detection method based on space-time neighborhood characteristics | |
| Song et al. | The research of real-time forest fire alarm algorithm based on video | |
| CN211509200U (en) | Transmission line prevents outer broken monitored control system based on artificial intelligence technique | |
| Jie et al. | Forest fire detection based on video multi-feature fusion | |
| CN1419361A (en) | Intelligent monitoring administration method for picture on network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200929 Termination date: 20211225 |